US10649787B2 - Exception handling involving emulation of exception triggering data transfer operation using syndrome data store that includes data value to be transferred - Google Patents

Exception handling involving emulation of exception triggering data transfer operation using syndrome data store that includes data value to be transferred Download PDF

Info

Publication number
US10649787B2
US10649787B2 US15/759,907 US201615759907A US10649787B2 US 10649787 B2 US10649787 B2 US 10649787B2 US 201615759907 A US201615759907 A US 201615759907A US 10649787 B2 US10649787 B2 US 10649787B2
Authority
US
United States
Prior art keywords
data
exception
syndrome
state
processing operation
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active, expires
Application number
US15/759,907
Other languages
English (en)
Other versions
US20180239607A1 (en
Inventor
Jason Parker
Richard Roy Grisenthwaite
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
ARM Ltd
Original Assignee
ARM Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by ARM Ltd filed Critical ARM Ltd
Assigned to ARM LIMITED reassignment ARM LIMITED ASSIGNMENT OF ASSIGNORS INTEREST (SEE DOCUMENT FOR DETAILS). Assignors: PARKER, JASON, GRISENTHWAITE, RICHARD ROY
Publication of US20180239607A1 publication Critical patent/US20180239607A1/en
Application granted granted Critical
Publication of US10649787B2 publication Critical patent/US10649787B2/en
Active legal-status Critical Current
Adjusted expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F9/00—Arrangements for program control, e.g. control units
    • G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
    • G06F9/30—Arrangements for executing machine instructions, e.g. instruction decode
    • G06F9/38—Concurrent instruction execution, e.g. pipeline or look ahead
    • G06F9/3861—Recovery, e.g. branch miss-prediction, exception handling
    • G06F9/3865—Recovery, e.g. branch miss-prediction, exception handling using deferred exception handling, e.g. exception flags
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F11/00—Error detection; Error correction; Monitoring
    • G06F11/07—Responding to the occurrence of a fault, e.g. fault tolerance
    • G06F11/0703—Error or fault processing not based on redundancy, i.e. by taking additional measures to deal with the error or fault not making use of redundancy in operation, in hardware, or in data representation
    • G06F11/0766—Error or fault reporting or storing
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F9/00—Arrangements for program control, e.g. control units
    • G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
    • G06F9/30—Arrangements for executing machine instructions, e.g. instruction decode
    • G06F9/30003—Arrangements for executing specific machine instructions
    • G06F9/3004—Arrangements for executing specific machine instructions to perform operations on memory
    • G06F9/30043—LOAD or STORE instructions; Clear instruction
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F9/00—Arrangements for program control, e.g. control units
    • G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
    • G06F9/30—Arrangements for executing machine instructions, e.g. instruction decode
    • G06F9/30098—Register arrangements
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F9/00—Arrangements for program control, e.g. control units
    • G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
    • G06F9/30—Arrangements for executing machine instructions, e.g. instruction decode
    • G06F9/38—Concurrent instruction execution, e.g. pipeline or look ahead
    • G06F9/3861—Recovery, e.g. branch miss-prediction, exception handling
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F9/00—Arrangements for program control, e.g. control units
    • G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
    • G06F9/44—Arrangements for executing specific programs
    • G06F9/455—Emulation; Interpretation; Software simulation, e.g. virtualisation or emulation of application or operating system execution engines
    • G06F9/45533—Hypervisors; Virtual machine monitors

Definitions

  • This disclosure relates to the field of data processing systems. More particularly, this disclosure relates to exception handling within data processing systems.
  • a hypervisor program may be providing a virtual execution environment for a guest operating system and application programs.
  • the guest operating system or application program may attempt a data access that is trapped as an exception and then emulated by the hypervisor.
  • the hypervisor may emulate the data access, it requires access to the state of the guest system.
  • it may be desired for security reasons that the hypervisor not be permitted to access the state of the guest system as the guest system contains private/secret/secure data.
  • At least some of the embodiments of the disclosure provide apparatus for processing data, comprising:
  • exception handling circuitry to detect attempted execution of an exception-triggering processing operation including a transfer of a data value with a given register of said plurality of registers and to trigger execution of exception handling program instructions to at least partially emulate said exception-triggering processing operation;
  • syndrome data store to store syndrome data characterising said exception-triggering processing operation and including said data value
  • said exception handling circuitry performs said transfer with said given register using said data value within said syndrome data.
  • At least some of the embodiments of the disclosure provide apparatus for processing data, comprising:
  • exception handling means for detecting attempted execution of an exception-triggering processing operation including a transfer of a data value with a given register means of said plurality of register means and for triggering execution of exception handling program instructions to at least partially emulate said exception-triggering processing operation;
  • syndrome data storage means for storing syndrome data characterising said exception-triggering processing operation and including said data value
  • said exception handling means performs said transfer with said given register means using said data value within said syndrome data.
  • At least some of the embodiments of the disclosure provide a method of processing data, comprising:
  • FIG. 1 schematically illustrates a data processing system
  • FIG. 2 is a flow diagram schematically illustrating exception handling
  • FIG. 3 is a diagram schematically illustrating a virtualisation program and guest programs.
  • FIG. 4 schematically illustrates a two-stage virtual-to-physical address translation.
  • FIG. 1 schematically illustrates a data processing system 2 including a processor core 4 connected via interconnect circuitry 6 to a memory 8 and one or more memory-mapped input/output devices 10 .
  • the memory 8 includes one or more private regions 13 storing data which is private to a guest program executing in a virtualised environment using the processor core 4 .
  • the memory 8 further includes one or more shared regions 12 which are shared between the guest program and a virtualisation program providing the virtualised execution environment to the guest program.
  • the virtualisation program may, for example, be a hypervisor program and the guest program may be a guest operating system program, which itself provides a virtualised execution environment to one or more application programs.
  • the processor core 4 includes an instruction fetch unit 14 , which fetches program instructions to be executed from the memory 8 and supplies these to a decoder 16 where the program instructions are decoded to generate control signals which then control other circuitry within the processor core 4 to perform the processing operation specified by the decoded program instructions.
  • the processor core 4 includes processing circuitry 18 including a register bank 20 (comprising a plurality of general purpose registers) to perform processing operations such as arithmetic operations and logic operations.
  • a load store unit 22 is used to perform memory access operations such as load operations in response to a load instruction (LDR) whereby a data value is read from the memory 8 and stored into a register of the register bank 20 .
  • LDR load instruction
  • the load store unit 22 also performs store operations specified by store instructions (STR) in which data values are read from registers of the register bank 20 and stored into memory addresses within the memory 8 .
  • STR store instructions
  • the input/output devices 10 are memory-mapped and so load instructions and store instructions may be used to read data values from the input/output devices 10 and store these into registers within the register bank 20 .
  • Store operations may similarly be used to read values from the register bank 20 and write these to the input/output devices 10 .
  • a memory management unit 24 uses page table data stored within the memory 8 to manage access to the memory address space (including the memory 8 and the input/output devices 10 ) by the memory access instructions executed on the processor core 4 .
  • the memory management unit 24 detects when a memory access is attempted which violates access permissions, or is otherwise not permitted. This gives rise to a data abort.
  • Exception handling circuitry 26 is responsive to the data abort indicated by the memory management unit 24 to trigger exception handling.
  • the exception handling response may include following an exception vector indicating the start address of exception handling program instructions to commence execution of those exception handling program instructions (e.g. load the vector address to the program counter).
  • the exception handling circuitry 26 may save status data representing a current processing state of the processor core 4 as held in a CPSR register 28 (current program status register) into a SPSR register 30 (saved program status register) from where the status data may be restored when the exception handling has completed and return is made to the initial program flow.
  • a syndrome register 32 is coupled to the exception handling circuitry 26 and stores data characterising an exception-triggering processing operation (at least for some memory accesses) which lead to the exception being handled by the exception handling circuitry 26 . In some embodiments more than one syndrome register may be used.
  • the syndrome register(s) is an example of a syndrome data store.
  • the syndrome data includes, for example: an address within the memory address space associated with the memory access that has aborted, a flag indicating whether the memory access was a write to that memory address or a read from that memory address, a size value indicating the size of the data value being accessed (e.g. byte, half word, word, double word, etc.).
  • the syndrome register contains the data value that was to be written. This data value may be supplied from the load store unit 22 to the syndrome register 32 .
  • the syndrome register 32 contains space into which that data value may be stored by the exception handling program instructions (performing exception handling processing operations) such that when the aborted memory access instruction is replayed, the read data value can be recovered from the syndrome register 32 and returned to the load store unit 22 and the processor core 4 (e.g. returned into the appropriate register of the register bank 20 ).
  • the data processing system 2 supports virtualisation whereby a hypervisor program provides a virtualised execution environment to one or more guest operating system programs and application programs.
  • the memory access data held by the memory management unit 24 may serve to deny the hypervisor the ability to access data associated with the guest program, such as data stored within private regions 13 belonging to that guest program.
  • the data stored within the register bank 20 during execution of the guest programs and other state data associated with the guest programs (e.g. CPSR data, state configuration data etc.) may also be kept private to the guest program.
  • the hypervisor program operates to trap memory access by the guest programs to certain memory addresses, such as the memory-mapped input/output devices 10 .
  • the hypervisor program emulates such trapped memory accesses on behalf of the guest programs using exception handling program instructions to perform exception handling processing operations.
  • guest program may seek to perform a write of a data value to a memory mapped input/output device.
  • the memory management unit 24 using its page table data, detects that the write access is one to be trapped and emulated by the hypervisor program and accordingly raises a data abort exception which is passed to the exception handling circuitry 26 .
  • the exception handling circuitry 26 saves data characterising the aborted write into the syndrome register 32 .
  • This data characterising the write includes a flag indicating that the aborted operation is a write operation, the address of the attempted write operation, the data value to be written by the attempted write operation, the size of the data value to be written, and further data (such as the replay state data discussed below) as may be useful in emulating the aborted write operation.
  • the exception handling circuitry also stores the current program status register contents 28 into the saved program status register 30 .
  • the contents of the syndrome register 32 prior to the aborted write operation constitute part of the current program state and accordingly are also saved as part of the exception handling. Should a further exception arise during the emulation of the aborted memory access, then the current syndrome data at that time will similarly be saved as part of the current program status data so that it can be restored as the exceptions unwind.
  • Exception handling program instructions triggered by the data abort of the attempted write operation serve to read the syndrome data from the syndrome register 32 and use this data to complete the intended write operation. This completion may involve, for example, translating an address of the write specified by the guest program into a different address to be used by the exception handling program instructions which operate as part of the hypervisor program and which correspond to the physical address of the memory mapped input output devices 10 as managed by the hypervisor program.
  • the exception handling program instructions read from the syndrome register 32 a memory address to be read and then perform that read from the appropriate memory address as managed by the hypervisor program.
  • the data value returned from this read is stored into the syndrome register 32 as part of the syndrome data.
  • the aborting memory access instruction (whether a write or a read) is issued for re-execution.
  • the data value stored within the syndrome register 32 by the exception processing which emulated that read is then returned as a result of that read, e.g. stored into the appropriate destination register of the register bank 20 as specified by the original read instruction.
  • the emulating exception processing program instructions will have already performed the write operation specified in behalf of the guest program and so the write program instruction may be completed (retired) without further action being necessary.
  • the syndrome register 32 stores as part of the syndrome data replayed state data.
  • This replayed state data may be a flag having either a first state or a second state.
  • the replayed state data is used to indicate that an aborting memory access instruction has already been emulated when execution of that memory access instruction is attempted again. Thus, when an aborting memory access instruction is first encountered within the program flow of the guest program, it triggers exception processing and is emulated by the exception handling program instructions.
  • the replay state data (which may be part of the syndrome data or held elsewhere) is set to a first state.
  • the exception handling circuitry 26 detects that the replay state data has the first state and accordingly detects that the aborting memory access has already been emulated. If the aborting memory access is a write, then the exception handling circuitry 26 can simply mark that write as completed as the emulation that was previously performed has already performed the desired write. In the case that the aborting memory access is a read, then the syndrome register 32 contains the data value returned for that read by the emulating exception handling program instructions. In this case, the exception handling circuitry 26 uses that data value from the syndrome register 32 and supplies it as the result of the data read (e.g. transfers the read data from the syndrome register 32 to the appropriate destination register within the register bank 20 specified by the aborting read instruction) and then processes the read instruction as complete.
  • the exception handling circuitry 26 uses that data value from the syndrome register 32 and supplies it as the result of the data read (e.g. transfers the read data from the syndrome register 32 to the appropriate destination register within the register bank 20 specified by the aborting read instruction) and then processes the read instruction as
  • FIG. 2 is a flow diagram schematically illustrating exception handling data aborts.
  • processing waits until a data abort arises. Other types of exception may be handled in a different way.
  • the exception handling circuitry 26 at step 29 serves to access the syndrome data register 32 .
  • Step 31 determines whether or not the replay state data accessed within the syndrome register 32 has a second state. If the replay state data has the second state, then this indicates that the aborting memory access instruction has not already been emulated.
  • step 33 sets the replay state data to the first state such that when the aborting memory access is encountered again then it may be detected that it has already been emulated.
  • Step 34 determines whether the aborting memory access is a load instruction. If the aborting memory access is a load instruction, then step 36 serves to store into the syndrome register 32 , as part of the syndrome data characterising that load instruction, data including the memory address that is the target of the load instruction, the data size of the load instruction and a flag indicating that the aborting memory access is a read. If determination at step 34 is that the aborting memory access is a store instruction (i.e.
  • step 38 serves to store into the syndrome register 32 as part of the syndrome data, a target address of the store instruction, the data value to be written as part of the store instruction, the data size of the data value as well as a flag indicating that the aborting memory access was a write.
  • step 40 serves to trigger execution of exception handling instructions.
  • This triggering may take the form of following an exception vector set up as part of the configuration of the data processing system 2 in respect of data aborts, with this vector being used to set the program counter value such that execution of the exception handling program instructions is commenced.
  • Step 42 is performed by the exception handling program instructions and determines whether the abort instruction is a load. This determination may be performed by examining the read/write flag within the syndrome data stored in the syndrome register 32 as set at steps 36 and 38 . If the aborting memory access being emulated is a load, then step 44 serves to emulate that load by reading the data value from the memory address in the syndrome register (or a translated version of that memory address), storing the read data value returned from the data read back into the syndrome register 32 , and performing any further actions necessary to complete the emulation of the aborted read operation.
  • step 46 serves to complete that store operation by writing the data value stored in the syndrome register 32 to the memory address (or a translated version of that memory address) as indicated by the memory address stored within the syndrome register 32 .
  • step 48 a return from the exception is performed by returning to the abort triggering program instruction.
  • the exception handling program instructions may perform other operations during the exception handling and emulation operation, such as dealing with the storing of other program state and the restoring of that program state.
  • step 48 processing returns to step 27 .
  • step 48 has returned processing to the abort triggering instruction (aborting memory access within the guest program)
  • step 27 will detect that this instruction again aborts as a consequence of the same protection by the memory management unit 24 .
  • the determination at step 30 will be that the replay state data does not equal the second state, and accordingly processing proceeds to step 50 .
  • Step 50 sets the replay state data to the second state.
  • Step 52 detects if the memory access instruction is a load. If the aborting memory access instruction is a load, then step 54 serves to return the data value stored within the syndrome register value 32 as the result of the aborting load instruction. Step 56 then retires the instruction by marking it as complete and processing returns to step 27 . If the determination at step 52 is that the aborting memory access instruction is not a load, then step 54 is bypassed and processing proceeds directly to step 56 where the aborting memory access instruction, which in this case is a store, is retired and marked as complete.
  • the flow diagram illustrated in FIG. 2 includes some steps which are performed by hardware (e.g. by the exception handling circuitry 26 ) and some steps which are performed by software.
  • the steps marked with “*” are performed by software using the exception handling program instructions.
  • the other processing steps are performed under hardware control by the exception handling circuitry 26 , and other elements within the data processing system 2 as acquired. It will be appreciated that in other embodiments different divisions between the steps which are performed in hardware and software may be used.
  • FIG. 3 schematically illustrates the relationship between a virtualisation program, in the form of a hypervisor program 58 , and guest programs in the form of guest operating systems 60 , 62 and application programs 64 , 66 , 68 , 70 .
  • the hypervisor program 58 operates at a higher level of privilege (exception level) than the guest programs 60 - 70 .
  • the hypervisor program 58 provides a virtualised execution environment for the guest programs 60 - 70 . As part of this virtualised execution, the hypervisor program 58 provides virtual access to the input/output devices 10 .
  • the hypervisor program 58 may also virtualise access to other memory addresses or resources of the data processing system 2 , such as system configuration registers.
  • the present techniques utilising the syndrome register 32 may be used to provide for the emulation of other exception triggering processing operations by exception handling program instructions e.g. trapped accesses to system registers.
  • the emulation may also be performed using the syndrome data stored within the syndrome register 32 without requiring the emulation to have access to private data of the guest program.
  • the data required to perform the emulation may be stored under hardware control into the syndrome register 32 from where it can be read by the emulating program instructions.
  • FIG. 4 schematically illustrates a two-stage address translation performed by the memory management unit 24 .
  • An application program 64 , 66 , 68 , 70 may generate a memory access instruction using a virtual address.
  • a first stage translation 72 is then performed by the memory management unit 24 using page table data controlled by the appropriate guest operating system 60 , 62 to form an intermediate physical address corresponding to the physical address as provided by the guest operating system 60 , 62 .
  • the guest operating system 60 , 62 is itself executing in a virtualised environment and accordingly the memory management unit 24 performs a second stage translation 74 using page table data managed by the hypervisor 58 to produce a physical address which then addresses the memory address space including the memory 8 and the input/output devices 10 .
  • the physical address produced by the second stage translation 74 corresponds the hypervisors view of the physical memory address space.
  • the first stage translation 72 uses page table data managed by the guest operating system 60 , 62 .
  • This first stage translation 72 may serve to block attempted memory accesses by the hypervisor program 58 to the private regions 13 within the memory 8 which are private to the guest operating system 60 , 62 (or application programs 64 - 70 ). Even though the hypervisor program 58 has a higher level of privilege than the guest operating system 60 , 62 , the first stage translation 72 as managed by the guest operating system 60 , 62 may block the hypervisor from accessing data. Page table data corresponding to the first stage translation 72 may be stored within the private region 13 to protect its security.
  • the second stage translation 74 is performed using page table data managed by the hypervisor program 58 .
  • This second stage translation data 74 may be used to trap memory accesses by the guest operating systems 60 , 62 to memory addresses, such as the input output devices 10 , that are controlled by the hypervisor program 58 and require emulation by the hypervisor program 58 using the syndrome register 32 and the syndrome data discussed above.
  • the above described example embodiments use the replay state data to control behaviour upon attempted re-execution of an exception triggering program instruction.
  • Alternative example embodiments may not need to use such replay state data.
  • the exception handling program instructions may restart execution after the exception handling using the program instruction following the Store instruction (i.e. re-execution of the Store instruction is not attempted).
  • the need for use of the replay state data may be avoided by the provision and use of a new instruction at the end of the exception handling program instructions that controls the exception handling circuitry to blind copy the data value from the syndrome register to its intended destination register before returning execution to the instruction following the Load instruction.

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Software Systems (AREA)
  • Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Quality & Reliability (AREA)
  • Executing Machine-Instructions (AREA)
  • Storage Device Security (AREA)
  • Memory System Of A Hierarchy Structure (AREA)
  • Microcomputers (AREA)
  • Debugging And Monitoring (AREA)
US15/759,907 2015-10-14 2016-09-09 Exception handling involving emulation of exception triggering data transfer operation using syndrome data store that includes data value to be transferred Active 2036-10-01 US10649787B2 (en)

Applications Claiming Priority (3)

Application Number Priority Date Filing Date Title
GB1518165.4 2015-10-14
GB1518165.4A GB2543306B (en) 2015-10-14 2015-10-14 Exception handling
PCT/GB2016/052784 WO2017064453A1 (en) 2015-10-14 2016-09-09 Exception handling

Publications (2)

Publication Number Publication Date
US20180239607A1 US20180239607A1 (en) 2018-08-23
US10649787B2 true US10649787B2 (en) 2020-05-12

Family

ID=55131018

Family Applications (1)

Application Number Title Priority Date Filing Date
US15/759,907 Active 2036-10-01 US10649787B2 (en) 2015-10-14 2016-09-09 Exception handling involving emulation of exception triggering data transfer operation using syndrome data store that includes data value to be transferred

Country Status (9)

Country Link
US (1) US10649787B2 (ko)
EP (1) EP3341834B1 (ko)
JP (1) JP6920286B2 (ko)
KR (1) KR102613643B1 (ko)
CN (1) CN108139906B (ko)
GB (1) GB2543306B (ko)
IL (1) IL257898B (ko)
TW (1) TWI724034B (ko)
WO (1) WO2017064453A1 (ko)

Families Citing this family (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
GB2579617B (en) * 2018-12-06 2021-01-27 Advanced Risc Mach Ltd An apparatus and method for handling exception causing events
FR3100901B1 (fr) * 2019-09-12 2021-08-27 Stmicroelectronics Grand Ouest Sas Système de protection de la mémoire
US11816217B2 (en) * 2020-04-10 2023-11-14 Vmware, Inc. Decoy memory allocation

Citations (19)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US5327567A (en) * 1989-11-16 1994-07-05 Texas Instruments Incorporated Method and system for returning emulated results from a trap handler
US5751945A (en) * 1995-10-02 1998-05-12 International Business Machines Corporation Method and system for performance monitoring stalls to identify pipeline bottlenecks and stalls in a processing system
US6189093B1 (en) 1998-07-21 2001-02-13 Lsi Logic Corporation System for initiating exception routine in response to memory access exception by storing exception information and exception bit within architectured register
US6615343B1 (en) * 2000-06-22 2003-09-02 Sun Microsystems, Inc. Mechanism for delivering precise exceptions in an out-of-order processor with speculative execution
US6904517B2 (en) * 2000-11-27 2005-06-07 Arm Limited Data processing apparatus and method for saving return state
US20050177666A1 (en) * 2004-02-11 2005-08-11 Paul Kimelman Interrupt processing control
US20060156074A1 (en) * 2004-12-02 2006-07-13 Cisco Technology, Inc. (A California Corporation) Method and apparatus for utilizing an exception handler to avoid hanging up a CPU when a peripheral device does not respond
US20060251092A1 (en) * 2005-05-04 2006-11-09 Arm Limited Data processing system
US20070005858A1 (en) * 2005-06-30 2007-01-04 Intel Corporation Extended message signal interrupt
US20080155167A1 (en) * 2006-12-20 2008-06-26 David Hennah Mansell Handling access requests in a data processing apparatus
US20080216073A1 (en) * 1999-01-28 2008-09-04 Ati International Srl Apparatus for executing programs for a first computer architechture on a computer of a second architechture
GB2460280A (en) 2008-05-23 2009-11-25 Advanced Risc Mach Ltd Using a memory-abort register in the emulation of memory access operations
US8135894B1 (en) * 2009-07-31 2012-03-13 Altera Corporation Methods and systems for reducing interrupt latency by using a dedicated bit
US20120260073A1 (en) * 2011-04-07 2012-10-11 Via Technologies, Inc. Emulation of execution mode banked registers
US20130185720A1 (en) * 2012-01-17 2013-07-18 Vmware, Inc. User-mode system-level mobile virtualization
US20150261590A1 (en) * 2014-03-15 2015-09-17 Zeev Sperber Conditional memory fault assist suppression
US20150347137A1 (en) * 2014-06-02 2015-12-03 International Business Machines Corporation Suppressing Branch Prediction on a Repeated Execution of an Aborted Transaction
US9317452B1 (en) * 2013-11-18 2016-04-19 Amazon Technologies, Inc. Selective restrictions to memory mapped registers using an emulator
US20160239209A1 (en) * 2015-02-13 2016-08-18 Google Inc. Transparent hardware-assisted memory decompression

Family Cites Families (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN100392618C (zh) * 1997-08-11 2008-06-04 全斯美达有限公司 保护计算机内存储器被写入的系统、方法和设备
US7802080B2 (en) * 2004-03-24 2010-09-21 Arm Limited Null exception handling
CN102460376B (zh) * 2009-06-26 2016-05-18 英特尔公司 无约束事务存储器(utm)系统的优化
US9244686B2 (en) * 2011-04-07 2016-01-26 Via Technologies, Inc. Microprocessor that translates conditional load/store instructions into variable number of microinstructions

Patent Citations (20)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US5327567A (en) * 1989-11-16 1994-07-05 Texas Instruments Incorporated Method and system for returning emulated results from a trap handler
US5751945A (en) * 1995-10-02 1998-05-12 International Business Machines Corporation Method and system for performance monitoring stalls to identify pipeline bottlenecks and stalls in a processing system
US6189093B1 (en) 1998-07-21 2001-02-13 Lsi Logic Corporation System for initiating exception routine in response to memory access exception by storing exception information and exception bit within architectured register
US20080216073A1 (en) * 1999-01-28 2008-09-04 Ati International Srl Apparatus for executing programs for a first computer architechture on a computer of a second architechture
US6615343B1 (en) * 2000-06-22 2003-09-02 Sun Microsystems, Inc. Mechanism for delivering precise exceptions in an out-of-order processor with speculative execution
US6904517B2 (en) * 2000-11-27 2005-06-07 Arm Limited Data processing apparatus and method for saving return state
US20050177666A1 (en) * 2004-02-11 2005-08-11 Paul Kimelman Interrupt processing control
US20060156074A1 (en) * 2004-12-02 2006-07-13 Cisco Technology, Inc. (A California Corporation) Method and apparatus for utilizing an exception handler to avoid hanging up a CPU when a peripheral device does not respond
US20060251092A1 (en) * 2005-05-04 2006-11-09 Arm Limited Data processing system
US20070005858A1 (en) * 2005-06-30 2007-01-04 Intel Corporation Extended message signal interrupt
US20080155167A1 (en) * 2006-12-20 2008-06-26 David Hennah Mansell Handling access requests in a data processing apparatus
GB2460280A (en) 2008-05-23 2009-11-25 Advanced Risc Mach Ltd Using a memory-abort register in the emulation of memory access operations
US20100094613A1 (en) * 2008-05-23 2010-04-15 Arm Limited Device emulation support within a host data processing apparatus
US8135894B1 (en) * 2009-07-31 2012-03-13 Altera Corporation Methods and systems for reducing interrupt latency by using a dedicated bit
US20120260073A1 (en) * 2011-04-07 2012-10-11 Via Technologies, Inc. Emulation of execution mode banked registers
US20130185720A1 (en) * 2012-01-17 2013-07-18 Vmware, Inc. User-mode system-level mobile virtualization
US9317452B1 (en) * 2013-11-18 2016-04-19 Amazon Technologies, Inc. Selective restrictions to memory mapped registers using an emulator
US20150261590A1 (en) * 2014-03-15 2015-09-17 Zeev Sperber Conditional memory fault assist suppression
US20150347137A1 (en) * 2014-06-02 2015-12-03 International Business Machines Corporation Suppressing Branch Prediction on a Repeated Execution of an Aborted Transaction
US20160239209A1 (en) * 2015-02-13 2016-08-18 Google Inc. Transparent hardware-assisted memory decompression

Non-Patent Citations (5)

* Cited by examiner, † Cited by third party
Title
International Search Report and Written Opinion of the ISA for PCT/GB2016/052784, dated Dec. 16, 2016, 10 pages.
Office Action in corresponding European Application No. 16 766 055.4-1203 dated Feb. 5, 2020, 4 pages.
Pfoh et al., "Exploiting the x86 Architecture to Derive Virtual Machine State Information", Emerging Security Information Systems and Technologies (Secureware), Jul. 18, 2010, pp. 166-175.
Search Report for GB1518165.4, dated Apr. 14, 2016, 4 pages.
Sfezer, J et al. Architectural Support for Hypervisor-Secure Virtualization. Proceedings of ASPLOS XVII, 2012, p. 437-450 [online], retrieved Jul. 16, 2019. Retrieved from the Internet <URL: https://dl.acm.org/citation.cfm?id=2151022> <DOI=http://dx.doi.org/10.1145/2150976.2151022>. *

Also Published As

Publication number Publication date
JP6920286B2 (ja) 2021-08-18
KR102613643B1 (ko) 2023-12-14
US20180239607A1 (en) 2018-08-23
GB2543306B (en) 2019-05-01
EP3341834A1 (en) 2018-07-04
CN108139906A (zh) 2018-06-08
WO2017064453A1 (en) 2017-04-20
TW201715408A (zh) 2017-05-01
IL257898B (en) 2020-03-31
KR20180067581A (ko) 2018-06-20
CN108139906B (zh) 2022-09-02
TWI724034B (zh) 2021-04-11
EP3341834B1 (en) 2021-05-12
GB2543306A (en) 2017-04-19
JP2018531462A (ja) 2018-10-25
IL257898A (en) 2018-05-31
GB201518165D0 (en) 2015-11-25

Similar Documents

Publication Publication Date Title
US8561060B2 (en) Processor and method configured to determine an exit mechanism using an intercept configuration for a virtual machine
RU2686552C2 (ru) Системы и способы предоставления результата текущей команды процессора при выходе из виртуальной машины
TWI509518B (zh) 用於改良巢式虛擬化之性能的方法、中央處理單元裝置及系統
US8099541B2 (en) Minivisor entry point in virtual machine monitor address space
US8656222B2 (en) Method and system for recording a selected computer process for subsequent replay
US9171159B2 (en) Performing security operations using binary translation
CN108351826B (zh) 监视处理器的操作
US20160034300A1 (en) Information processing devicing and method
US20160048458A1 (en) Computer Security Systems and Methods Using Hardware-Accelerated Access To Guest Memory From Below The Operating System
US10649787B2 (en) Exception handling involving emulation of exception triggering data transfer operation using syndrome data store that includes data value to be transferred
US10963280B2 (en) Hypervisor post-write notification of control and debug register updates
US9898307B2 (en) Starting application processors of a virtual machine
JP2018531462A6 (ja) 例外処理
JP2011523741A (ja) ホストデータ処理装置内におけるデバイスエミュレーションのサポート
US9383935B1 (en) Secondary CPU MMU initialization using page fault exception
US10496461B2 (en) Apparatus and method for hardware initiation of emulated instructions
US11216280B2 (en) Exception interception
JP7369720B2 (ja) アクションをトリガするための装置及び方法
US10698783B2 (en) Virtualization detection in a computing system
JP2018036695A (ja) 情報処理監視装置、情報処理監視方法、監視プログラム、記録媒体及び情報処理装置
US20150186140A1 (en) Opcode trapping

Legal Events

Date Code Title Description
AS Assignment

Owner name: ARM LIMITED, UNITED KINGDOM

Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNORS:PARKER, JASON;GRISENTHWAITE, RICHARD ROY;SIGNING DATES FROM 20180226 TO 20180312;REEL/FRAME:045203/0198

FEPP Fee payment procedure

Free format text: ENTITY STATUS SET TO UNDISCOUNTED (ORIGINAL EVENT CODE: BIG.); ENTITY STATUS OF PATENT OWNER: LARGE ENTITY

STPP Information on status: patent application and granting procedure in general

Free format text: DOCKETED NEW CASE - READY FOR EXAMINATION

STPP Information on status: patent application and granting procedure in general

Free format text: NON FINAL ACTION MAILED

STPP Information on status: patent application and granting procedure in general

Free format text: RESPONSE TO NON-FINAL OFFICE ACTION ENTERED AND FORWARDED TO EXAMINER

STPP Information on status: patent application and granting procedure in general

Free format text: NOTICE OF ALLOWANCE MAILED -- APPLICATION RECEIVED IN OFFICE OF PUBLICATIONS

STPP Information on status: patent application and granting procedure in general

Free format text: AWAITING TC RESP., ISSUE FEE NOT PAID

STCF Information on status: patent grant

Free format text: PATENTED CASE

MAFP Maintenance fee payment

Free format text: PAYMENT OF MAINTENANCE FEE, 4TH YEAR, LARGE ENTITY (ORIGINAL EVENT CODE: M1551); ENTITY STATUS OF PATENT OWNER: LARGE ENTITY

Year of fee payment: 4